AI RESEARCH
Neural Configuration-Space Barriers for Manipulation Planning and Control
arXiv CS.LG
•
ArXi:2503.04929v3 Announce Type: replace-cross Planning and control for high-dimensional robot manipulators in cluttered dynamic environments require computational efficiency and robust safety guarantees. Inspired by recent advances in learning configuration-space distance functions (CDFs) as representations of robot bodies, we propose a unified approach for motion planning and control that formulates safety constraints as CDF barriers. A CDF barrier approximates the local free configuration space, substantially reducing the number of collision-checking operations during motion planning.